{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3NPUND6RPMVZDXN5XEN77OCNG4","short_pith_number":"pith:3NPUND6R","schema_version":"1.0","canonical_sha256":"db5f468fd17b2b91ddbdb91bffb84d3734251a9be48bf94922e6b2a757be2c70","source":{"kind":"arxiv","id":"2303.11511","version":3},"attestation_state":"computed","paper":{"title":"STDLens: Model Hijacking-Resilient Federated Learning for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Fatih Ilhan, Ka-Ho Chow, Ling Liu, Wenqi Wei, Yanzhao Wu","submitted_at":"2023-03-21T00:15:53Z","abstract_excerpt":"Federated Learning (FL) has been gaining popularity as a collaborative learning framework to train deep learning-based object detection models over a distributed population of clients. Despite its advantages, FL is vulnerable to model hijacking. The attacker can control how the object detection system should misbehave by implanting Trojaned gradients using only a small number of compromised clients in the collaborative learning process. This paper introduces STDLens, a principled approach to safeguarding FL against such attacks. We first investigate existing mitigation mechanisms and analyze t"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2303.11511","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-03-21T00:15:53Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"214592a575029dab7720aa4ffab2c69b374ec701c7a37ee5d6dc81c827bfa46a","abstract_canon_sha256":"d9e76f4afb10da8671afa76962b632978481b0f980804a2cbbab9103a4b1bc13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:01.124241Z","signature_b64":"i1FIOAk5qngSere4g7jZ1uXBJLXNtsyRN+Cejk3Ib+oY6Bwj9H7kuYr50Y1zqdeqxN6Ih5UmNkmd9M1NgMpHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db5f468fd17b2b91ddbdb91bffb84d3734251a9be48bf94922e6b2a757be2c70","last_reissued_at":"2026-07-05T06:12:01.123865Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:01.123865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STDLens: Model Hijacking-Resilient Federated Learning for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CR","authors_text":"Fatih Ilhan, Ka-Ho Chow, Ling Liu, Wenqi Wei, Yanzhao Wu","submitted_at":"2023-03-21T00:15:53Z","abstract_excerpt":"Federated Learning (FL) has been gaining popularity as a collaborative learning framework to train deep learning-based object detection models over a distributed population of clients. Despite its advantages, FL is vulnerable to model hijacking. The attacker can control how the object detection system should misbehave by implanting Trojaned gradients using only a small number of compromised clients in the collaborative learning process. This paper introduces STDLens, a principled approach to safeguarding FL against such attacks. We first investigate existing mitigation mechanisms and analyze t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.11511","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.11511/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2303.11511","created_at":"2026-07-05T06:12:01.123927+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.11511v3","created_at":"2026-07-05T06:12:01.123927+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.11511","created_at":"2026-07-05T06:12:01.123927+00:00"},{"alias_kind":"pith_short_12","alias_value":"3NPUND6RPMVZ","created_at":"2026-07-05T06:12:01.123927+00:00"},{"alias_kind":"pith_short_16","alias_value":"3NPUND6RPMVZDXN5","created_at":"2026-07-05T06:12:01.123927+00:00"},{"alias_kind":"pith_short_8","alias_value":"3NPUND6R","created_at":"2026-07-05T06:12:01.123927+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4","json":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4.json","graph_json":"https://pith.science/api/pith-number/3NPUND6RPMVZDXN5XEN77OCNG4/graph.json","events_json":"https://pith.science/api/pith-number/3NPUND6RPMVZDXN5XEN77OCNG4/events.json","paper":"https://pith.science/paper/3NPUND6R"},"agent_actions":{"view_html":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4","download_json":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4.json","view_paper":"https://pith.science/paper/3NPUND6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.11511&json=true","fetch_graph":"https://pith.science/api/pith-number/3NPUND6RPMVZDXN5XEN77OCNG4/graph.json","fetch_events":"https://pith.science/api/pith-number/3NPUND6RPMVZDXN5XEN77OCNG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4/action/storage_attestation","attest_author":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4/action/author_attestation","sign_citation":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4/action/citation_signature","submit_replication":"https://pith.science/pith/3NPUND6RPMVZDXN5XEN77OCNG4/action/replication_record"}},"created_at":"2026-07-05T06:12:01.123927+00:00","updated_at":"2026-07-05T06:12:01.123927+00:00"}